Dataset Information

Impact of signal intensity normalization of MRI on the generalizability of radiomic-based prediction of molecular glioma subtypes.

ABSTRACT:

Objectives

Radiomic features have demonstrated encouraging results for non-invasive detection of molecular biomarkers, but the lack of guidelines for pre-processing MRI-data has led to poor generalizability. Here, we assessed the influence of different MRI-intensity normalization techniques on the performance of radiomics-based models for predicting molecular glioma subtypes.

Methods

Preoperative MRI-data from n = 615 patients with newly diagnosed glioma and known isocitrate dehydrogenase (IDH) and 1p/19q status were pre-processed using four different methods: no normalization (naive), N4 bias field correction (N4), N4 followed by either WhiteStripe (N4/WS), or z-score normalization (N4/z-score). A total of 377 Image-Biomarker-Standardisation-Initiative-compliant radiomic features were extracted from each normalized data, and 9 different machine-learning algorithms were trained for multiclass prediction of molecular glioma subtypes (IDH-mutant 1p/19q codeleted vs. IDH-mutant 1p/19q non-codeleted vs. IDH wild type). External testing was performed in public glioma datasets from UCSF (n = 410) and TCGA (n = 160).

Results

Support vector machine yielded the best performance with macro-average AUCs of 0.84 (naive), 0.84 (N4), 0.87 (N4/WS), and 0.87 (N4/z-score) in the internal test set. Both N4/WS and z-score outperformed the other approaches in the external UCSF and TCGA test sets with macro-average AUCs ranging from 0.85 to 0.87, replicating the performance of the internal test set, in contrast to macro-average AUCs ranging from 0.19 to 0.45 for naive and 0.26 to 0.52 for N4 alone.

Conclusion

Intensity normalization of MRI data is essential for the generalizability of radiomic-based machine-learning models. Specifically, both N4/WS and N4/z-score approaches allow to preserve the high model performance, yielding generalizable performance when applying the developed radiomic-based machine-learning model in an external heterogeneous, multi-institutional setting.

Clinical relevance statement

Intensity normalization such as N4/WS or N4/z-score can be used to develop reliable radiomics-based machine learning models from heterogeneous multicentre MRI datasets and provide non-invasive prediction of glioma subtypes.

Key points

• MRI-intensity normalization increases the stability of radiomics-based models and leads to better generalizability. • Intensity normalization did not appear relevant when the developed model was applied to homogeneous data from the same institution. • Radiomic-based machine learning algorithms are a promising approach for simultaneous classification of IDH and 1p/19q status of glioma.

SUBMITTER: Foltyn-Dumitru M

PROVIDER: S-EPMC10957611 | biostudies-literature | 2024 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Impact of signal intensity normalization of MRI on the generalizability of radiomic-based prediction of molecular glioma subtypes.

Foltyn-Dumitru Martha M Schell Marianne M Rastogi Aditya A Sahm Felix F Kessler Tobias T Wick Wolfgang W Bendszus Martin M Brugnara Gianluca G Vollmuth Philipp P

European radiology 20230906 4

<h4>Objectives</h4>Radiomic features have demonstrated encouraging results for non-invasive detection of molecular biomarkers, but the lack of guidelines for pre-processing MRI-data has led to poor generalizability. Here, we assessed the influence of different MRI-intensity normalization techniques on the performance of radiomics-based models for predicting molecular glioma subtypes.<h4>Methods</h4>Preoperative MRI-data from n = 615 patients with newly diagnosed glioma and known isocitrate dehyd ...[more]

PMID: 37672053

Similar Datasets

Project description:Widespread clinical use of MRI radiomic tumor profiling for prognostication and treatment planning in cancers faces major obstacles due to limitations in standardization of radiomic features. The purpose of the current work was to assess the impact of different MRI scanning- and normalization protocols for the statistical analyses of tumor radiomic data in two patient cohorts with uterine endometrial-(EC) (n = 136) and cervical (CC) (n = 132) cancer. 1.5 T and 3 T, T1-weighted MRI 2 min post-contrast injection, T2-weighted turbo spin echo imaging, and diffusion-weighted imaging were acquired. Radiomic features were extracted from within manually segmented tumors in 3D and normalized either using z-score normalization or a linear regression model (LRM) accounting for linear dependencies with MRI acquisition parameters. Patients were clustered into two groups based on radiomic profile. Impact of MRI scanning parameters on cluster composition and prognostication were analyzed using Kruskal-Wallis tests, Kaplan-Meier plots, log-rank test, random survival forests and LASSO Cox regression with time-dependent area under curve (tdAUC) (α = 0.05). A large proportion of the radiomic features was statistically associated with MRI scanning protocol in both cohorts (EC: 162/385 [42%]; CC: 180/292 [62%]). A substantial number of EC (49/136 [36%]) and CC (50/132 [38%]) patients changed cluster when clustering was performed after z-score-versus LRM normalization. Prognostic modeling based on cluster groups yielded similar outputs for the two normalization methods in the EC/CC cohorts (log-rank test; z-score: p = 0.02/0.33; LRM: p = 0.01/0.45). Mean tdAUC for prognostic modeling of disease-specific survival (DSS) by the radiomic features in EC/CC was similar for the two normalization methods (random survival forests; z-score: mean tdAUC = 0.77/0.78; LRM: mean tdAUC = 0.80/0.75; LASSO Cox; z-score: mean tdAUC = 0.64/0.76; LRM: mean tdAUC = 0.76/0.75). Severe biases in tumor radiomics data due to MRI scanning parameters exist. Z-score normalization does not eliminate these biases, whereas LRM normalization effectively does. Still, radiomic cluster groups after z-score- and LRM normalization were similarly associated with DSS in EC and CC patients.

Project description:ObjectivesRadiomics is a promising avenue in non-invasive characterisation of diffuse glioma. Clinical translation is hampered by lack of reproducibility across centres and difficulty in standardising image intensity in MRI datasets. The study aim was to perform a systematic review of different methods of MRI intensity standardisation prior to radiomic feature extraction.MethodsMEDLINE, EMBASE, and SCOPUS were searched for articles meeting the following eligibility criteria: MRI radiomic studies where one method of intensity normalisation was compared with another or no normalisation, and original research concerning patients diagnosed with diffuse gliomas. Using PRISMA criteria, data were extracted from short-listed studies including number of patients, MRI sequences, validation status, radiomics software, method of segmentation, and intensity standardisation. QUADAS-2 was used for quality appraisal.ResultsAfter duplicate removal, 741 results were returned from database and reference searches and, from these, 12 papers were eligible. Due to a lack of common pre-processing and different analyses, a narrative synthesis was sought. Three different intensity standardisation techniques have been studied: histogram matching (5/12), limiting or rescaling signal intensity (8/12), and deep learning (1/12)-only two papers compared different methods. From these studies, histogram matching produced the more reliable features compared to other methods of altering MRI signal intensity.ConclusionMultiple methods of intensity standardisation have been described in the literature without clear consensus. Further research that directly compares different methods of intensity standardisation on glioma MRI datasets is required.Key points• Intensity standardisation is a key pre-processing step in the development of robust radiomic signatures to evaluate diffuse glioma. • A minority of studies compared the impact of two or more methods. • Further research is required to directly compare multiple methods of MRI intensity standardisation on glioma datasets.

Project description:ObjectivesAn easy-to-implement MRI model for predicting partial response (PR) postradiotherapy for diffuse intrinsic pontine glioma (DIPG) is lacking. Utilizing quantitative T2 signal intensity and introducing a visual evaluation method based on T2 signal intensity heterogeneity, and compared MRI radiomic models for predicting radiotherapy response in pediatric patients with DIPG.MethodsWe retrospectively included patients with brainstem gliomas aged ≤ 18 years admitted between July 2011 and March 2023. Applying Response Assessment in Pediatric Neuro-Oncology criteria, we categorized patients into PR and non-PR groups. For qualitative analysis, tumor heterogeneity vision was classified into four grades based on T2-weighted images. Quantitative analysis included the relative T2 signal intensity ratio (rT2SR), extra pons volume ratio, and tumor ring-enhancement volume. Radiomic features were extracted from T2-weighted and T1-enhanced images of volumes of interest. Univariate analysis was used to identify independent variables related to PR. Multivariate logistic regression was performed using significant variables (p < 0.05) from univariate analysis.ResultsOf 140 patients (training n = 109, and test n = 31), 64 (45.7%) achieved PR. The AUC of the predictive model with extrapontine volume ratio, rT2SRmax-min (rT2SRdif), and grade was 0.89. The AUCs of the T2-weighted and T1WI-enhanced models with radiomic signatures were 0.84 and 0.81, respectively. For the 31 DIPG test sets, the AUCs were 0.91, 0.83, and 0.81, for the models incorporating the quantitative features, radiomic model (T2-weighted images, and T1W1-enhanced images), respectively.ConclusionCombining T2-weighted quantification with qualitative and extrapontine volume ratios reliably predicted pediatric DIPG radiotherapy response.Clinical relevance statementCombining T2-weighted quantification with qualitative and extrapontine volume ratios can accurately predict diffuse intrinsic pontine glioma (DIPG) radiotherapy response, which may facilitate personalized treatment and prognostic assessment for patients with DIPG.Key pointsEarly identification is crucial for radiotherapy response and risk stratification in diffuse intrinsic pontine glioma. The model using tumor heterogeneity and quantitative T2 signal metrics achieved an AUC of 0.91. Using a combination of parameters can effectively predict radiotherapy response in this population.

Project description:ObjectivesWe previously demonstrated the potential of radiomics for the prediction of severe histological placenta accreta spectrum (PAS) subtypes using T2-weighted MRI. We aim to validate our model using an additional dataset. Secondly, we explore whether the performance is improved using a new approach to develop a new multivariate radiomics model.MethodsMulti-centre retrospective analysis was conducted between 2018 and 2023. Inclusion criteria: MRI performed for suspicion of PAS from ultrasound, clinical findings of PAS at laparotomy and/or histopathological confirmation. Radiomic features were extracted from T2-weighted MRI. The previous multivariate model was validated. Secondly, a 5-radiomic feature random forest classifier was selected from a randomized feature selection scheme to predict invasive placenta increta PAS cases. Prediction performance was assessed based on several metrics including area under the curve (AUC) of the receiver operating characteristic curve (ROC), sensitivity, and specificity.ResultsWe present 100 women [mean age 34.6 (±3.9) with PAS], 64 of whom had placenta increta. Firstly, we validated the previous multivariate model and found that a support vector machine classifier had a sensitivity of 0.620 (95% CI: 0.068; 1.0), specificity of 0.619 (95% CI: 0.059; 1.0), an AUC of 0.671 (95% CI: 0.440; 0.922), and accuracy of 0.602 (95% CI: 0.353; 0.817) for predicting placenta increta. From the new multivariate model, the best 5-feature subset was selected via the random subset feature selection scheme comprised of 4 radiomic features and 1 clinical variable (number of previous caesareans). This clinical-radiomic model achieved an AUC of 0.713 (95% CI: 0.551; 0.854), accuracy of 0.695 (95% CI 0.563; 0.793), sensitivity of 0.843 (95% CI 0.682; 0.990), and specificity of 0.447 (95% CI 0.167; 0.667).ConclusionWe validated our previous model and present a new multivariate radiomic model for the prediction of severe placenta increta from a well-defined, cohort of PAS cases.Advances in knowledgeRadiomic features demonstrate good predictive potential for identifying placenta increta. This suggests radiomics may be a useful adjunct to clinicians caring for women with this high-risk pregnancy condition.

Dataset Information

Impact of signal intensity normalization of MRI on the generalizability of radiomic-based prediction of molecular glioma subtypes.

Objectives

Methods

Results

Conclusion

Clinical relevance statement

Key points

Publications

Impact of signal intensity normalization of MRI on the generalizability of radiomic-based prediction of molecular glioma subtypes.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets